Information processing device, information processing method, and information processing program

Abstract

To provide a summary with high visual appeal in the summarization of a posted comment.SOLUTION: An information processing device comprises an acquisition unit, a generation unit, and a provision unit. The acquisition unit acquires a summarization request for comments posted in relation to a predetermined article. When the acquisition unit acquires the summarization request, the generation unit uses the comments to generate proposal information encouraging a user to refer to the comments and a summary of the comments. The provision unit provides the proposal information and summary generated by the generation unit.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, a technique for providing comments posted on an article that can be viewed via the Internet to viewers of the article is known.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, there is room for further improvement in providing a highly attractive summary in the summary of the posted comment.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of providing a highly attractive summary in the summary of a posted comment.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes an acquisition unit that acquires a summary request for a comment posted on a predetermined article, and when the acquisition unit acquires the summary request, uses the comment to generate proposal information for prompting a user to refer to the comment and a summary of the comment, and a providing unit that provides the proposal information and the summary generated by the generation unit.

Effects of the Invention

[0007] According to one embodiment, the summarization of posted comments has the effect of providing a highly attractive summary. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of the configuration of an information processing system according to an embodiment. [Figure 2] Figure 2 shows an example of information processing according to the present invention. [Figure 3A] Figure 3A shows an example of a UI screen according to the embodiment. [Figure 3B] Figure 3B shows an example of a UI screen (summary request screen) according to the embodiment. [Figure 3C] Figure 3C shows an example of a UI screen (loading screen) according to this embodiment. [Figure 3D] Figure 3D shows an example of a UI screen (summary display screen) according to the embodiment. [Figure 4] Figure 4 shows an example of the configuration of a terminal device according to this embodiment. [Figure 5] Figure 5 shows an example of the configuration of an information processing device according to the embodiment. [Figure 6] Figure 6 shows an example of an article information storage unit according to the embodiment. [Figure 7] Figure 7 shows an example of a cache information storage unit according to the embodiment. [Figure 8] Figure 8 is a flowchart showing an example of information processing according to the embodiment. [Figure 9] Figure 9 is a hardware configuration diagram showing an example of a computer that implements the functions of an information processing device. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] (Embodiment) [1. Configuration of the Information Processing System] The information processing system 1 shown in Figure 1 will now be described. As shown in Figure 1, the information processing system 1 includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) by wired or wireless means. Figure 1 is a diagram showing an example configuration of the information processing system 1 according to an embodiment.

[0011] Terminal device 10 is an information processing device used by users who view articles via the internet. Users view articles (e.g., news articles) distributed through a designated web service, for example. Users also view (or attempt to view) comments posted by other readers of an article. Terminal device 10 can be any device as long as it can implement the processing described in the embodiment. Terminal device 10 may also be a smartphone, tablet, notebook PC, desktop PC, mobile phone, PDA, or other device. Figure 2 shows the case where terminal device 10 is a smartphone.

[0012] Terminal device 10 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 4G-5G (Generation) or LTE (Long Term Evolution). Terminal device 10 also has a screen, such as an LCD display, which has touch panel functionality and may accept various operations on displayed data such as content from the user, such as tapping, sliding, and scrolling, using a finger or stylus. In Figure 2, terminal device 10 is used by user U1.

[0013] The information processing device 100 is an information processing device aimed at providing highly attractive summaries of posted comments, and can be any device as long as it can realize the processing in the embodiment. The information processing device 100 can be realized by, for example, a server device or cloud system that provides a predetermined article that a user is viewing, or a server device or cloud system that provides a predetermined web service to which such predetermined article is distributed. For example, when the information processing device 100 receives a request to summarize a posted comment made for a predetermined article, it provides a summary of the posted comment. Specifically, when the information processing device 100 receives a request to summarize a posted comment made for a predetermined article, it generates a summary of the posted comment and information to encourage the user to refer to the posted comment (hereinafter referred to as "appeal points" as appropriate), and by providing this information, it becomes possible to provide a highly attractive summary. In addition, since the information processing device 100 can provide appeal points along with the summary, it can encourage the user to refer to the posted comment.

[0014] The information processing apparatus 100 has a model. The model is, for example, a text generation model that has learned data such as data published on the Internet. For example, the model is a GPT (Generative Pre-trained Transformer) model that generates an answer to a question. Such a model generates an answer to a question from data published on the Internet. Since new data is published on the Internet every day, the answers generated by the model are updated every day. That is, even if the same question is asked, the data referred to by the model when generating an answer differs depending on the timing of the question, etc., and thus different answers are generated. Also, since the model can provide detailed answers to questions in a wide range of fields, a wide variety of questions are asked by users to the model.

[0015] Note that in FIG. 1, the case where the terminal device 10 and the information processing apparatus 100 are separate devices is shown, but the terminal device 10 and the information processing apparatus 100 may be integrated.

[0016] 〔2. An Example of Information Processing〕 FIG. 2 is a diagram showing an example of information processing of the information processing system 1 according to the embodiment. FIGS. 3A to 3D are diagrams showing an example of a UI screen according to the embodiment. The UI screens shown in FIGS. 3A to 3D are UI screens displayed on the terminal device 10. Hereinafter, FIG. 2 will be described using FIGS. 3A to 3D as appropriate. The user U1 is browsing an article K1 (for example, a news article distributed by a predetermined web service or the like) via the Internet and is browsing (or about to browse) the posted comments of the viewers of the article K1 posted on the article K1. Note that the posted comments of the viewers of the article K1 are assumed to be comments such as the opinions and views of the viewers regarding the content of the article K1, but any comment written by the viewer in the posting form can be a posted comment. Also, the article K1 can be an article in any category (for example, a news article or the like), and can be an article such as sports, entertainment, events, and accidents.

[0017] On the terminal device 10, for example, screen G1 shown in Figure 3A is displayed, and user U1 is viewing the posted comments on screen G1. In Figure 3A, the details of article K1 (article content) are displayed in area R1 of screen G1, and the posted comments are displayed in area R2. Area R2 is, in other words, the area for organizing the posted comments. Area R2 may display the number of posted comments (one or more posted comments), but on screen G1, only a portion of the posted comments are displayed. Also, on screen G1, only a portion of the posted comments are viewable, and to view more posted comments, the "See More" button in area R3 is required. The order in which the posted comments are displayed in area R2 can be based on any indicator or criterion and is not particularly limited. Furthermore, area R3 is the area for requesting an increase in the number of posted comments displayed in area R2. That is, area R3 is the area for requesting that more (or all) of the posted comments be displayed in area R2. When area R3 is operated (for example, by clicking or tapping), the screen displayed on the terminal device 10 transitions from screen G1 to screen G2 as shown in Figure 3B. In other words, when area R3 is operated, screen G2 is displayed on the terminal device 10.

[0018] Screen G2 displays an area R2 for displaying posted comments, similar to Screen G1, and an area R4 for requesting a summary of the posted comments. Area R4 indicates that the comments will be summarized by AI. Note that more posted comments may be displayed in area R2 on screen G2 than on screen G1. Area R4 is displayed, for example, below the posting form "Write a comment" for user U1 to post a comment. Note that the display manner and position of area R4 are not limited to being displayed below the posting form in this way. When area R4 is operated, the screen displayed on the terminal device 10 transitions from screen G2 to screen G4 shown in Figure 3D, via screen G3 shown in Figure 3C. That is, when area R4 is operated, screen G4 is displayed on the terminal device 10, for example, after screen G3 is displayed. Screen G3 is a screen that is temporarily displayed when area R4 is operated until the summarization process is completed, and after the summarization process is completed, the screen automatically switches to screen G4.

[0019] Screen G3 is a screen that appears, for example, when area R4 is operated at a predetermined time (a loading screen for processing the summarization of posted comments). For example, screen G3 is the screen that appears when a summary of posted comments for article K1 is first requested. In other words, for example, screen G3 is a screen that is only displayed to the user who first operates area R4 on the screen for posted comments of article K1. Also, for example, if a cache of posted comments is generated at a predetermined frequency, this screen is displayed when a new cache is generated. For example, if a cache is generated every hour, this screen is displayed to the user who first operates area R4 more than one hour after the most recent cache was generated. This is because when a cache is generated, the posted comments used for summarization (posted comments that meet the predetermined conditions described later) are temporarily stored. Such posted comments are stored until a new cache is generated, and when a new cache is generated, the posted comments used for summarization are updated, so the summarization of posted comments needs to be processed again and screen G3 is displayed. If no cache is generated, the summarization of posted comments may be performed in real time each time area R4 is manipulated (in this case, screen G3 will be displayed each time area R4 is manipulated), or the summarization of posted comments may be performed only the first time area R4 is manipulated (in this case, screen G3 will be displayed only the first time area R4 is manipulated). Also, the same number of posted comments as in screen G2 may be displayed in area R2 on screen G3.

[0020] Screen G4 displays an area R2 for organizing posted comments, similar to Screen G1; an area R5 for displaying summaries of posted comments; an area R6 for displaying selling points; and an area R7 for displaying related words (such as related keywords). Area R5 displays a summary generated using a predetermined number of posted comments that rank highly when all posted comments for article K1 are sorted in a predetermined order (for example, an order based on indicators such as the number of "likes," views, and ratings widely used on SNS (Social Networking Services)). For example, area R5 displays a summary generated using only the posted comments with the highest number of "likes." In other words, only a predetermined number of posted comments that rank highly when sorted in a predetermined order are included in the summary. Note that it is not limited to summarizing only a predetermined number of posted comments; for example, all posted comments with a number of "likes," views, ratings, etc. above a predetermined threshold may be included in the summary. Of course, a summary may also be generated using all posted comments submitted for article K1. Furthermore, whether or not a comment posted to article K1 is eligible for summarization may be determined based on whether or not the total number of comments posted to article K1 is above a predetermined threshold. In this case, if the total number of comments posted to article K1 is above a predetermined threshold, it may be determined that the comment posted to article K1 is eligible for summarization. If it is determined that the comment posted to article K1 is eligible for summarization, a summary may be generated using the comments from the total number of comments posted to article K1 that satisfy the predetermined conditions. Also, if a cache is saved, the comment posted in this way that is eligible for summarization is temporarily saved. For example, if a cache is saved, it is temporarily saved until a new cache is generated, and when a new cache is generated, the comment posted that was eligible for summarization at the time of the new cache generation is temporarily saved. In this way, if a cache is saved, the temporary saving of the comment posted is repeated.

[0021] Area R5 displays two types of summaries: those generated based on comments that meet certain criteria for being included in summaries, and those generated based on comments that do not meet the specified criteria. The former can be a summary that is likely to garner broad support, while the latter can be a summary that does not manipulate public opinion in the former way. Thus, since opinions that only meet the specified criteria, as in the former case, may sometimes manipulate public opinion, displaying opinions that do not meet the specified criteria, as in the latter case, helps to prevent such manipulation. Note that the latter is a summary generated based on comments that do not meet the specified criteria, but it may also be a summary generated based on comments that meet the specified criteria among the comments that do not meet the specified criteria. Screen G4 displays two types of summaries generated so that the text is connected to "What are the main comments?" (Screen G4 shows "I think that tax cuts are more effective than subsidies for stabilizing gasoline prices" and "There are also opinions that the overall economic situation should be improved so that people can cover their living expenses, rather than focusing on the gasoline price issue"). Details of summary generation will be described later.

[0022] Area R6 displays the appeal points. These appeal points are information intended to encourage users to refer to the comments posted in Area R2, but they may also be information summarizing the key points to read in the comments in Area R2. Alternatively, the appeal points may be information summarizing the important points for reading the summary in Area R5. Furthermore, the appeal points may be information generated to make users want to read the summary in Area R5. Since the appeal points are generated using the comments that were summarized in the summary in Area R5, Area R6 displays appeal points generated based on such comments. On screen G4, appeal points generated so that the text connects to "Pay attention" (on screen G4, "Deep insight into the gasoline price problem") are displayed. Details of how appeal points are generated will be described later.

[0023] In area R7, related words are displayed. Related words may be words highly relevant to the posted comments in area R2 (or posted comments that meet certain conditions), or words highly relevant to the summary in area R5. For example, related words may be words that frequently appear in the posted comments in area R2 (or posted comments that meet certain conditions), or words that co-occur with words that frequently appear in the posted comments in area R2. For example, they may be words extracted as important words from the top posted comments. Also, for example, related words may be words that frequently appear in the summary in area R5, or words that co-occur with words that frequently appear in the summary in area R5. Since related words are generated using the posted comments that were summarized in the summary in area R5, area R7 displays related words generated based on such summaries. On screen G4, related words generated so that the sentence connects to "What are the related words?" (on screen G4, "gasoline prices, subsidies, taxes") are displayed. Details of the generation of related words will be described later.

[0024] Furthermore, since comments posted on article K1 are subject to summarization, and information encouraging users to refer to comments in area R2 is displayed as an appeal point in area R6, only direct comments posted on article K1 are subject to summarization. In other words, comments (replies) to comments (parent comments) on article K1 are excluded from summarization.

[0025] Furthermore, the summaries displayed in area R5 may be summaries that have been generated so that a portion of them conforms to a predetermined format. For example, they may be summaries that have been generated so that they do not use strong language or so as not to manipulate public opinion. For example, they may be summaries that have been generated so that the endings of sentences are softened.

[0026] The following describes the information processing of the information processing system 1 according to the embodiment. When user U1 operates area R4 shown on screen G2, terminal device 10 receives user U1's operation on area R4 and transmits user U1's operation information on area R4 to information processing device 100 (step S101). When information processing device 100 obtains user U1's operation information on area R4, it receives (obtains) a request to summarize the posted comments on article K1. In this case, for example, when information processing device 100 receives a request to summarize the posted comments, it may perform a process to display screen G3 on terminal device 10 until the summarization process is completed.

[0027] When the information processing device 100 receives a summary request, it uses the posted comments (area R2 shown in screen G2) submitted to article K1 to generate a summary of the posted comments (area R5 shown in screen G4), appealing points (area R6 shown in screen G4), and related words (area R7 shown in screen G4). In this case, the information processing device 100 uses all or part of the posted comments (area R2 shown in screen G2) submitted to article K1 to generate a summary of the posted comments (area R5 shown in screen G4), appealing points (area R6 shown in screen G4), and related words (area R7 shown in screen G4). The following explanation will describe, as an example, the case in which the information processing device 100 uses some of the posted comments submitted to article K1 to generate a summary of the posted comments (area R5 shown in screen G4), appealing points (area R6 shown in screen G4), and related words (area R7 shown in screen G4).

[0028] The information processing device 100 extracts comments from all comments posted to article K1 that meet predetermined conditions for being subject to summarization (step S102). For example, the information processing device 100 extracts comments that rank highly when all comments posted to article K1 are sorted in a predetermined order. In this case, the information processing device 100 may extract comments that rank highly in real time at the time the summarization request is received, or, if a cache is stored, it may retrieve comments that are temporarily stored as a cache. In the latter case, when the information processing device 100 receives the summarization request, it may determine whether a cache is stored (or whether there is a stored cache), and if a cache is stored (or if there is a stored cache), it may retrieve the stored comments, and if no cache is stored, it may extract comments using the former method.

[0029] The information processing device 100 uses the extracted (or acquired) posted comments to generate a summary of the posted comments (area R5 shown in screen G4), appealing points (area R6 shown in screen G4), and related words (area R7 shown in screen G4). In this process, the information processing device 100 uses a GPT model to generate the summary of the posted comments (area R5 shown in screen G4), appealing points (area R6 shown in screen G4), and related words (area R7 shown in screen G4). Here, the GPT model according to the embodiment will be described. The GPT model according to the embodiment is a model that, for example, when a comment and a prompt are input, outputs a summary of the comment, appealing points, and related words using the input comment according to the input prompt.

[0030] Examples of prompts for generating comment summaries from comments include, for example, "Pick one opinion with a predetermined tendency from the given comment data and summarize it" and "Pick one opinion that does not follow the predetermined tendency from the given comment data and summarize it." The former is a prompt for generating summaries of the predetermined tendency, and the latter is a prompt for generating summaries of the other tendency. The GPT model generates comment summaries by using these two types of prompts together. Another example of a prompt for generating appeal points from comments is, for example, "Output the points that make the given comment data worth reading as 'appeal points' in a sentence of XX characters or less." The GPT model generates appeal points for comments by using such prompts. Another example of a prompt for generating related words from comments is, for example, "Extract multiple important keywords from the given comment data." The GPT model generates related words for comments by using such prompts.

[0031] The information processing device 100 inputs the posted comment extracted (or acquired) in step S102 into the GPT model along with the prompt described above, thereby generating a summary of the posted comment (area R5 shown on screen G4), its selling points (area R6 shown on screen G4), and related words (area R7 shown on screen G4) (step S103). The information processing device 100 then transmits this generated information to the terminal device 10 (step S104). Upon receiving the information transmitted from the information processing device 100, the terminal device 10 displays screen G4, which contains the summary of the posted comment, its selling points, and related words in predetermined areas corresponding to the area R4 operated by user U1, for the article K1 that user U1 is viewing.

[0032] In the above embodiment, the information processing device 100 may generate a summary of the posted comment (area R5 shown on screen G4) by using prompts for generating a summary in a tone that does not manipulate public opinion. For example, the information processing device 100 may generate a summary of the posted comment (area R5 shown on screen G4) by using prompts for generating a summary in which the endings of sentences and other elements are softened.

[0033] [3. Configuration of the terminal device] Next, the configuration of the terminal device 10 according to the embodiment will be described using Figure 4. Figure 4 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Figure 4, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0034] (Communications Section 11) The communication unit 11 is implemented, for example, by a NIC (Network Interface Card). The communication unit 11 is connected to a predetermined network N by wire or wireless connection and sends and receives information to and from the information processing device 100 via the predetermined network N.

[0035] (Input section 12) The input unit 12 receives various operations from the user. In Figure 2, it receives various operations from user U1. For example, the input unit 12 may receive various operations from the user via the display surface using a touch panel function. Alternatively, the input unit 12 may receive various operations from buttons provided on the terminal device 10, or from a keyboard or mouse connected to the terminal device 10.

[0036] (Output section 13) The output unit 13 is a display screen for a tablet terminal, for example, which is implemented using a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various types of information. For example, the output unit 13 displays content (for example, summaries, selling points, related words, etc.) based on information transmitted from the information processing device 100.

[0037] (Control Unit 14) The control unit 14 is, for example, a controller, and is implemented by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in the internal memory of the terminal device 10 using RAM (Random Access Memory) as the working area. For example, these various programs include application programs installed on the terminal device 10. For example, these various programs include application programs that display content based on information transmitted from the information processing device 100. The control unit 14 is also implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0038] As shown in Figure 4, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0039] (Receiver 141) The receiving unit 141 receives information transmitted from, for example, the information processing device 100. For example, as feedback on the user's operation, the receiving unit 141 receives information such as summaries of comments posted on a predetermined article that the user is viewing, as well as selling points and related keywords.

[0040] (Transmitter 142) The transmitting unit 142 transmits, for example, user operation information to the terminal device 10. For example, the transmitting unit 142 transmits operation information performed by the user on the UI screen of a posted comment on a predetermined article that the user is viewing. For example, the transmitting unit 142 transmits operation information performed by the user to request a summary of the posted comment (i.e., a request to summarize the posted comment).

[0041] [4. Configuration of the Information Processing Device] Next, the configuration of the information processing device 100 according to the embodiment will be described using Figure 5. Figure 5 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 5, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 may also have an input unit (for example, a keyboard or mouse) that receives various operations from the administrator of the information processing device 100, and a display unit (for example, a liquid crystal display) for displaying various information.

[0042] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC. The communication unit 110 is connected to the network N by wire or wireless connection and sends and receives information to and from terminal devices 10, etc., via the network N.

[0043] (Storage unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as hard disks and optical discs. As shown in Figure 5, the storage unit 120 has an article information storage unit 121 and a cache information storage unit 122.

[0044] The article information storage unit 121 stores information about articles that can be viewed on a predetermined service. For example, the article information storage unit 121 stores information such as the content, title, category, and distribution date and time of the article, the video (including images) included in the article, the posted comments on the article, and the number of posted comments. Here, Figure 6 shows an example of the article information storage unit 121 according to the embodiment. As shown in Figure 6, the article information storage unit 121 has items such as "article ID," "article," and "post." The "article" further has items such as "content," "title," "category," "distribution date and time," and "video." The "post" further has items such as "posted comments" and "number of posts."

[0045] "Article ID" indicates identification information for identifying an article. "Content" indicates the content of the article. In the example shown in Figure 6, conceptual information such as "Content #1" and "Content #2" is shown as being stored in "Content," but in reality, the text of the article is stored there. "Title" indicates the title of the article. In the example shown in Figure 6, conceptual information such as "Title #1" and "Title #2" is shown as being stored in "Title," but in reality, the text of the title is stored there. "Category" indicates the category of the article (e.g., sports, entertainment, incidents and accidents). The category may also be, for example, controversial, royal family, politics, international, domestic, LGBT, lifestyle, etc. "Distribution Date and Time" indicates the distribution date and time of the article. "Video" indicates the video included in the article. In the example shown in Figure 6, conceptual information such as "Video #1" and "Video #2" is shown as being stored in "Video," but in reality, image data is stored there. In addition, for example, the URL where the image data is located or the file path name indicating the storage location may be stored there.

[0046] "Posted Comments" indicates the posted comments. In the example shown in Figure 6, conceptual information such as "Posted Comment #1" and "Posted Comment #2" is stored in "Posted Comments," but in reality, the text of the posted comments is stored there. "Number of Posts" indicates the number of posts.

[0047] The cache information storage unit 122 stores information about the generated cache when a cache is generated. Here, Figure 7 shows an example of the cache information storage unit 122 according to the embodiment. As shown in Figure 7, the cache information storage unit 122 has items such as "cache ID", "article ID", and "cache". The "cache" further has items such as "posted comment" and "generation date and time".

[0048] The "Cache ID" indicates identification information used to identify the cache. The "Article ID" indicates identification information used to identify the article. The "Posted Comment" indicates the posted comment extracted when the cache was created. In the example shown in Figure 7, conceptual information such as "Posted Comment #1" and "Posted Comment #2" is shown as being stored in "Posted Comment," but in reality, the text of the posted comment is stored there. The "Generation Date and Time" indicates the date and time the cache was created.

[0049] (Control unit 130) The control unit 130 is a controller, and is implemented, for example, by a CPU or MPU executing various programs stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 130 can be implemented by an integrated circuit such as an ASIC or FPGA.

[0050] As shown in Figure 5, the control unit 130 includes an acquisition unit 131, a determination unit 132, an extraction unit 133, a generation unit 134, and a provision unit 135, and realizes or executes the information processing operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 5, and other configurations are also acceptable as long as they perform the information processing described later.

[0051] (Acquisition part 131) The acquisition unit 131 acquires various information from the storage unit 120. The acquisition unit 131 also stores the acquired information in the storage unit 120.

[0052] The acquisition unit 131 acquires various information from external information processing devices. The acquisition unit 131 also acquires various information from other information processing devices such as the terminal device 10.

[0053] The acquisition unit 131, for example, acquires (accepts) requests to summarize posted comments. For example, the acquisition unit 131 acquires operational information for requesting a summary of posted comments made for a specific article that the user is viewing.

[0054] (Judgment unit 132) The determination unit 132 determines, for example, whether each of the comments posted to a specified article for which a user has requested a summary is eligible for summarization. For example, the determination unit 132 determines whether the total number of comments posted to the specified article for which a user has requested a summary is above a predetermined threshold. If it is above the predetermined threshold, it determines that the article is eligible for summarization; otherwise, it determines that the article is not eligible for summarization. The determination unit 132 may also, for example, notify the user that there are not enough comments for summarization if it determines that the article is not eligible for summarization. For example, the determination unit 132 may notify the user that the summary result is not complete and therefore will not be displayed. In such cases, the determination unit 132 may make area R3 on the UI screen inactive (unoperable) until the article becomes eligible for summarization, preventing the user from requesting a summary. Furthermore, the determination unit 132 determines whether the publication date and time of the specified article for which a user has requested a summary falls within a predetermined period. If it falls within the predetermined period, it determines that the article is eligible for summarization; otherwise, it determines that the article is not eligible for summarization. Furthermore, if the determination unit 132 determines, for example, that the subject is not eligible for summarization, it may notify the user that the period for summarization has expired. In such cases, after the period for summarization has expired, the determination unit 132 may make area R3 inactive (unoperable) on the UI screen, preventing the user from requesting a summary. Thus, if the determination unit 132 needs to stop summarization, it may stop the entire summarization function.

[0055] (Extraction part 133) For example, if the determination unit 132 determines that each of the comments posted to a specified article for which a user has requested a summary is eligible for summarization, the extraction unit 133 extracts comments from all the comments posted to the specified article that satisfy the predetermined conditions for being eligible for summarization. For example, the extraction unit 133 extracts comments that rank highly when all the comments posted to the specified article are sorted in a predetermined order.

[0056] (Generation unit 134) The generation unit 134 generates summaries of posted comments, appeal points, and related words using, for example, the posted comments extracted by the extraction unit 133. For example, the generation unit 134 generates summaries of posted comments, appeal points, and related words by inputting posted comments and prompts into a GPT model. For example, the generation unit 134 generates summaries of posted comments by inputting a prompt into a GPT model instructing it to generate summaries of comments from comments. For example, the generation unit 134 generates summaries of posted comments with a predetermined tendency by inputting a prompt into a GPT model instructing it to generate summaries of comments with a predetermined tendency, and generates summaries of posted comments with a predetermined tendency by inputting a prompt into a GPT model instructing it to generate summaries of comments with a predetermined tendency. In addition, for example, the generation unit 134 generates appeal points of posted comments by inputting a prompt into a GPT model instructing it to generate appeal points of comments from comments. Furthermore, for example, the generation unit 134 generates related words for posted comments from posted comments by inputting a prompt to the GPT model instructing it to generate related words for comments from the comments.

[0057] (Provider 135) The providing unit 135 provides, for example, information generated by the generating unit 134. For example, the providing unit 135 provides information such as a summary of the posted comment, its selling points, and related words. For example, the providing unit 135 provides information for displaying a UI screen (for example, screen G4) that includes the summary of the posted comment, its selling points, and related words in predetermined areas (for example, areas R5 to R7). Also, for example, the providing unit 135 provides information for displaying a UI screen (for example, screen G2) that includes an area (for example, area R4) for accepting summary requests in response to user operations. Also, for example, the providing unit 135 provides information for displaying a UI screen (for example, screen G3) that indicates that a summary request has been accepted and a summary is being generated (for example, "The AI ​​is summarizing your comment"). Also, for example, the providing unit 135 provides information for displaying a UI screen (for example, screen G1) that includes an area (for example, area R3) for transitioning to a UI screen (for example, screen G2) that can accept summary requests.

[0058] [5. Information Processing Flow] Next, the information processing procedure by the information processing system 1 according to the embodiment will be explained using Figure 8. Figure 8 is a flowchart showing the information processing procedure by the information processing system 1 according to the embodiment.

[0059] As shown in Figure 8, the information processing device 100 obtains a request to summarize comments posted on a predetermined article that the user is viewing (step S201).

[0060] The information processing device 100 inputs the acquired post comments into a GPT model to generate a summary of the post comments and their selling points (step S202).

[0061] The information processing device 100 provides information for displaying a UI screen that includes the generated summary and selling points in predetermined areas (step S203).

[0062] [6. Effects] As described above, the information processing device 100 according to the embodiment includes an acquisition unit 131, a generation unit 134, and a provision unit 135. The acquisition unit 131 acquires requests to summarize comments posted to a predetermined article. When the acquisition unit 131 acquires a summary request, the generation unit 134 uses the comments to generate suggestion information to encourage users to refer to the comments, and a summary of the comments. The provision unit 135 provides the suggestion information and summary generated by the generation unit 134.

[0063] As a result, the information processing device 100 according to the embodiment can, for example, provide appealing points along with a summary, thereby providing a highly attractive summary of posted comments. Furthermore, the information processing device 100 according to the embodiment can, for example, enhance the service and strengthen its value by providing a function that brings out the current strengths of posted comments and conveys their appeal. In addition, the information processing device 100 according to the embodiment can, for example, make it possible to see at a glance which posted comments lead to empathy or insights. Therefore, the information processing device 100 according to the embodiment can provide a service that has an impact on users.

[0064] Furthermore, the suggested information is a summary of the key points to read in the comments.

[0065] As a result, the information processing device 100 according to this embodiment can, for example, provide appealing points that summarize the key points of a posted comment, making it easy for users to grasp the key points of a posted comment. Furthermore, the information processing device 100 according to this embodiment can, for example, make users feel more inclined to read the actual posted comments.

[0066] Furthermore, the proposed information summarizes the key points that are important when reading the summary.

[0067] As a result, the information processing device 100 according to this embodiment can, for example, provide appealing points that summarize the important points to read in the summary, making it easy for users to grasp the important points to read in the summary.

[0068] Furthermore, the proposed information is generated in a way that makes readers want to read the summary.

[0069] As a result, the information processing device 100 according to this embodiment can provide, for example, appealing points that are generated in a way that makes the summary desirable to read, thus providing a highly attention-grabbing summary.

[0070] Furthermore, the summary is a summary that has been generated so that certain parts of the summary conform to a predetermined format in order to avoid manipulating public opinion.

[0071] As a result, the information processing device 100 according to this embodiment can, for example, make the content of the summary milder so as not to manipulate public opinion.

[0072] Furthermore, the generation unit 134 generates related words associated with the comments, using the proposed information and summary along with the comments.

[0073] As a result, the information processing device 100 according to this embodiment can, for example, allow a user to easily grasp the content of the summary.

[0074] Furthermore, the generation unit 134 uses comments that meet predetermined conditions to generate suggestion information to encourage users to refer to the comments, as well as a summary of the comments.

[0075] As a result, the information processing device 100 according to the embodiment can generate summaries and selling points using only posted comments that meet predetermined conditions, for example, and thus can provide summaries that are more appealing.

[0076] Furthermore, the generation unit 134 uses comments that rank highly based on a predetermined indicator to generate suggestion information to encourage users to refer to the comments, as well as a summary of the comments.

[0077] As a result, the information processing device 100 according to the embodiment can generate summaries and appeal points using only the top-ranking posts based on factors such as the number of "likes," views, and ratings, thereby providing more attractive summaries.

[0078] Also, comments do not include comments on other comments.

[0079] As a result, the information processing device 100 according to the embodiment can generate summaries and selling points that more appropriately reflect the content of articles by, for example, using only direct posted comments.

[0080] Furthermore, the comments are comments that have been generated as cached data at a predetermined frequency.

[0081] As a result, the information processing device 100 according to this embodiment can reduce the processing load on summarization by enabling temporary storage as a cache, for example, eliminating the need to process summaries each time a summarization request is made.

[0082] [7. Hardware Configuration] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having the configuration shown in Figure 9. Figure 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0083] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, and controls various parts. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0084] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 acquires data from other devices via a predetermined communication network and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined communication network.

[0085] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600.

[0086] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 can be, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), tape media, magnetic recording medium, or semiconductor memory.

[0087] For example, when the computer 1000 functions as an information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0088] [8. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0089] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0090] Furthermore, the embodiments described above can be combined as appropriate, as long as the processing content is not contradictory.

[0091] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0092] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of symbols]

[0093] 1. Information Processing System 10 Terminal devices 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Article Information Storage Unit 122 Cache Information Storage Unit 130 Control Unit 131 Acquisition Department 132 Judgment section 133 Extraction part 134 Generation part 135 Provision Department 141 Receiving Unit 142 Transmitter N Network

Claims

1. A data acquisition unit that obtains requests to summarize comments posted on a given article, When the acquisition unit acquires a summary request, the generation unit generates suggestion information to prompt the user to refer to the comment, and a summary of the comment, using the comment. A providing unit that provides the proposed information and summary generated by the generation unit, It has, The generating unit is The proposed information is generated using the comments that were selected from the aforementioned comments for the summary. Two types of summaries are generated as summaries of the comments displayed on the same screen: a summary based on the first comment that exhibits a predetermined trend, and a summary based on the second comment that does not exhibit the predetermined trend. An information processing device characterized by the following:

2. The aforementioned proposed information is information generated by a text generation model via a prompt that instructs the model to generate information summarizing the key points of the aforementioned comments. The information processing apparatus according to feature 1.

3. The proposed information is generated by a text generation model via a prompt that instructs the model to generate information summarizing the key points for reading the summary. The information processing apparatus according to feature 1.

4. The proposed information is generated by a text generation model via prompts that instruct it to generate information that readers would likely want to read. The information processing apparatus according to feature 1.

5. The aforementioned summary is a summary generated by a text generation model via a prompt that instructs the model to generate a summary in a predetermined format that is less likely to manipulate public opinion. The information processing apparatus according to feature 1.

6. The generating unit is Using the aforementioned proposal information and summary, along with the comments, generate related words associated with the comments. The information processing apparatus according to feature 1.

7. The generating unit is Using comments that meet the specified conditions from among the aforementioned comments, we generate suggestion information to encourage users to refer to the aforementioned comments, and a summary of the aforementioned comments. The information processing apparatus according to feature 1.

8. The generating unit is Using the comments ranked highly based on predetermined indicators, the system generates suggestion information to encourage users to refer to the aforementioned comments, as well as a summary of the comments. The information processing apparatus according to feature 7.

9. The aforementioned comment does not include any comments on the comment. The information processing apparatus according to feature 1.

10. The aforementioned comments are comments that are generated as cached comments at a predetermined frequency. The information processing apparatus according to feature 1.

11. A method of information processing performed by a computer, The process involves obtaining a request to summarize comments posted on a given article, and If the acquisition process acquires a summary request, the generation process generates suggestion information to prompt the user to refer to the comment, and a summary of the comment, using the comment. A provision step provides the proposed information and summary generated by the generation step, Includes, The aforementioned generation step is The proposed information is generated using the comments that were selected from the aforementioned comments for the summary. Two types of summaries are generated as summaries of the comments displayed on the same screen: a summary based on the first comment that exhibits a predetermined trend, and a summary based on the second comment that does not exhibit the predetermined trend. An information processing method characterized by the following:

12. Procedure for obtaining a summary request for comments posted on a given article, If the acquisition procedure obtains a summary request, the generation procedure generates suggestion information to prompt the user to refer to the comment, and a summary of the comment, using the comment. A provision procedure that provides the proposed information and summary generated by the above generation procedure, Have the computer run it, The aforementioned generation procedure is: The proposed information is generated using the comments that were selected from the aforementioned comments for the summary. Two types of summaries are generated as summaries of the comments displayed on the same screen: a summary based on the first comment that exhibits a predetermined trend, and a summary based on the second comment that does not exhibit the predetermined trend. An information processing program characterized by the following features.

Images